Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2687 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0318. Min Range: -1.0318

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1185883 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9223. Min Act: -0.0000

Data Index: 413640 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 1.0318. Min Range: -1.0318

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1295609 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1460584 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 1.0318. Min Range: -1.0318

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1907019 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1103803 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1621912 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9430. Min Act: 0.0000

Data Index: 1460825 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1064545 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9449. Min Act: -0.0000

Data Index: 887103 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1291988 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1256939 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.9398. Min Act: -0.0000

Data Index: 419002 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1681653 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1333219 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.8054. Min Act: -0.0000

Data Index: 326777 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1075129 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1512977 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.7019. Min Act: -0.0000

Data Index: 450084 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.0318. Min Range: -1.0318

Max Act: 0.6616. Min Act: -0.0000

Data Index: 928990 (The Pile)

Max Activating Token Index: 337